paper-with-me

홈 › Papers

Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learning

2023-08-08 · ICCV 2023 1 · Hanjae Kim, Jiyoung Lee, Seongheon Park, Kwanghoon Sohn

Compositional zero-shot learning (CZSL) aims to recognize unseen compositions with prior knowledge of known primitives (attribute and object). Previous works for CZSL often suffer from grasping the contextuality between attribute and object, as well as the discriminability of visual features, and the long-tailed distribution of real-world compositional data. We propose a simple and scalable framework called Composition Transformer (CoT) to address these issues. CoT employs object and attribute experts in distinctive manners to generate representative embeddings, using the visual network hierarchically. The object expert extracts representative object embeddings from the final layer in a bottom-up manner, while the attribute expert makes attribute embeddings in a top-down manner with a proposed object-guided attention module that models contextuality explicitly. To remedy biased prediction caused by imbalanced data distribution, we develop a simple minority attribute augmentation (MAA) that synthesizes virtual samples by mixing two images and oversampling minority attribute classes. Our method achieves SoTA performance on several benchmarks, including MIT-States, C-GQA, and VAW-CZSL. We also demonstrate the effectiveness of CoT in improving visual discrimination and addressing the model bias from the imbalanced data distribution. The code is available at https://github.com/HanjaeKim98/CoT.

📄 PDF Abstract BibTeX arXiv:2308.04016

Code (1)

hanjaekim98/cot 공식 구현 pytorch

Tasks

AttributeCompositional Zero-Shot LearningObjectZero-Shot Learning

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Adam 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Residual Connection 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning

2025-06-26 · Xiao Zhang, Yongqiang Ma, Haodong Jing, Nanning Zheng

Compositional Zero-Shot Learning (CZSL) investigates compositional generalization capacity to recognize unknown state-object pairs based on learned primitive concepts. Existing CZSL methods typically derive primitives fe…

Compositional Zero-Shot LearningMixture-of-ExpertsZero-Shot Learning

Zero-shot Compositional Action Recognition with Neural Logic Constraints

2025-08-04 · Gefan Ye, Lin Li, Kexin Li, Jun Xiao 외 arxiv

Zero-shot compositional action recognition (ZS-CAR) aims to identify unseen verb-object compositions in the videos by exploiting the learned knowledge of verb and object primitives during training. Despite compositional …

Action Recognition

Learning Attention Propagation for Compositional Zero-Shot Learning

2022-10-20 · Muhammad Gul Zain Ali Khan, Muhammad Ferjad Naeem, Luc van Gool, Alain Pagani 외

Compositional zero-shot learning aims to recognize unseen compositions of seen visual primitives of object classes and their states. While all primitives (states and objects) are observable during training in some combin…

Compositional Zero-Shot LearningZero-Shot Learning

Prompting Language-Informed Distribution for Compositional Zero-Shot Learning

2023-05-23 · Wentao Bao, Lichang Chen, Heng Huang, Yu Kong

Compositional zero-shot learning (CZSL) task aims to recognize unseen compositional visual concepts, e.g., sliced tomatoes, where the model is learned only from the seen compositions, e.g., sliced potatoes and red tomato…

Compositional Zero-Shot LearningInformativenessZero-shot GeneralizationZero-Shot Learning

Learning Graph Embeddings for Compositional Zero-shot Learning

2021-02-03 · CVPR 2021 1 · Muhammad Ferjad Naeem, Yongqin Xian, Federico Tombari, Zeynep Akata

In compositional zero-shot learning, the goal is to recognize unseen compositions (e.g. old dog) of observed visual primitives states (e.g. old, cute) and objects (e.g. car, dog) in the training set. This is challenging …

Compositional Zero-Shot LearningGraph EmbeddingTransfer LearningZero-Shot Learning